幺幺零

Results 3 issues of 幺幺零

The released code uses the temporal Transformer, but temporal attention treats each frame equally. It seems that no use of tricks like TimeEmbedding in different frames. Does this mean that...

It seems that the fp16 setting is not effective. I tried to use fp16 manually, and offload the autoencoder and CLIP to cpu memory during ddim denoising, and can run...